Browsing by Author "Raslan, Ahmed M."

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Application of Lean Principles to Neurosurgical Procedures: The Case of Lumbar Spinal Fusion Surgery, a Literature Review and Pilot Series
    (Oxford, 2018) Liu, Jesse J.; Raskin, Jeffrey S.; Hardaway, Fran; Holste, Katherine; Brown, Sarah; Raslan, Ahmed M.; Neurological Surgery, School of Medicine
    BACKGROUND Delivery of higher value healthcare is an ultimate government and public goal. Improving efficiency by standardization of surgical steps can improve patient outcomes, reduce costs, and lead to higher value healthcare. Lean principles and methodology have improved timeliness in perioperative medicine; however, process mapping of surgery itself has not been performed. OBJECTIVE To apply Plan/Do/Study/Act (PDSA) cycles methodology to lumbar posterior instrumented fusion (PIF) using lean principles to create a standard work flow, identify waste, remove intraoperative variability, and examine feasibility among pilot cases. METHODS Process maps for 5 PIF procedures were created by a PDSA cycle from 1 faculty neurosurgeon at 1 institution. Plan, modularize PIF into basic components; Do, map and time components; Study, analyze results; and Act, identify waste. Waste inventories, spaghetti diagrams, and chartings of time spent per step were created. Procedural steps were broadly defined in order to compare steps despite the variability in PIF and were analyzed with box and whisker plots to evaluate variability. RESULTS Temporal variabilities in duration of decompression vs closure and hardware vs closure were significantly different (P = .003). Variability in procedural step duration was smallest for closure and largest for exposure. Wastes including waiting and instrument defects accounted for 15% and 66% of all waste, respectively. CONCLUSION This pilot series demonstrates that lean principles can standardize surgical workflows and identify waste. Though time and labor intensive, lean principles and PDSA methodology can be applied to operative steps, not just the perioperative period.
  • Thumbnail Image
    Item
    NuCLS: A scalable crowdsourcing approach and dataset for nucleus classification and segmentation in breast cancer
    (Oxford University Press, 2022) Amgad, Mohamed; Atteya, Lamees A.; Hussein, Hagar; Mohammed, Kareem Hosny; Hafiz, Ehab; Elsebaie, Maha A.T.; Alhusseiny, Ahmed M.; AlMoslemany, Mohamed Atef; Elmatboly, Abdelmagid M.; Pappalardo, Philip A.; Sakr, Rokia Adel; Mobadersany, Pooya; Rachid, Ahmad; Saad, Anas M.; Alkashash, Ahmad M.; Ruhban, Inas A.; Alrefai, Anas; Elgazar, Nada M.; Abdulkarim, Ali; Farag, Abo-Alela; Etman, Amira; Elsaeed, Ahmed G.; Alagha, Yahya; Amer, Yomna A.; Raslan, Ahmed M.; Nadim, Menatalla K.; Elsebaie, Mai A.T.; Ayad, Ahmed; Hanna, Liza E.; Gadallah, Ahmed; Elkady, Mohamed; Drumheller, Bradley; Jaye, David; Manthey, David; Gutman, David A.; Elfandy, Habiba; Cooper, Lee A.D.; Pathology and Laboratory Medicine, School of Medicine
    Background: Deep learning enables accurate high-resolution mapping of cells and tissue structures that can serve as the foundation of interpretable machine-learning models for computational pathology. However, generating adequate labels for these structures is a critical barrier, given the time and effort required from pathologists. Results: This article describes a novel collaborative framework for engaging crowds of medical students and pathologists to produce quality labels for cell nuclei. We used this approach to produce the NuCLS dataset, containing >220,000 annotations of cell nuclei in breast cancers. This builds on prior work labeling tissue regions to produce an integrated tissue region- and cell-level annotation dataset for training that is the largest such resource for multi-scale analysis of breast cancer histology. This article presents data and analysis results for single and multi-rater annotations from both non-experts and pathologists. We present a novel workflow that uses algorithmic suggestions to collect accurate segmentation data without the need for laborious manual tracing of nuclei. Our results indicate that even noisy algorithmic suggestions do not adversely affect pathologist accuracy and can help non-experts improve annotation quality. We also present a new approach for inferring truth from multiple raters and show that non-experts can produce accurate annotations for visually distinctive classes. Conclusions: This study is the most extensive systematic exploration of the large-scale use of wisdom-of-the-crowd approaches to generate data for computational pathology applications.